检索结果-内蒙古大学图书馆

Quaternion neural networks: A physics-incorporated intelligence framework

IEEE SIGNAL processing MAGAZINE 2024年第3期41卷 88-100页

作者： Hirose, Akira Shang, Fang Otsuka, Yuta Natsuaki, Ryo Matsumoto, Yuya Usami, Naoto Song, Yicheng Chen, Haotian Univ Tokyo Dept Elect Engn & Informat Syst Tokyo 1138656 Japan Univ Electrocommun Grad Sch Informat & Engn Tokyo 1828585 Japan NEC Corp Ltd Visual Intelligence Res Labs Kawasaki 2118666 Japan Japan Aerosp Explorat Agcy JAXA Inst Space & Astronaut Sci Sagamihara 2525210 Japan Univ Tokyo Dept Elect Engn & Informat Syst Tokyo Japan

Why quaternions in neural networks (NNs)? Are there quaternions in the human brain? "No" may be an ordinary answer. However, quaternion NNs (QNNs) are a powerful framework that strongly connects artificial intelligence (AI) and the real world. In this article, we deal with NNs based on quaternions and describe their basics and features. We also detail the underlying ideas in their engineering applications, especially when we adaptively process the polarization information of electromagnetic waves. We focus on their role in remote sensing, such as Earth observation radar mounted on artificial satellites or aircraft and underground radar, as well as mobile communication. There, QNNs are a class of NNs that know physics, especially polarization, composing a framework by fusing measurement physics with adaptive-processing mathematics. This fusion realizes a seamless integration of measurement and intelligence, contributing to the construction of a human society having harmony between AI and real human lives.

关键词： Radar remote sensing Quaternions image processing Airborne radar artificial neural networks Mobile communication artificial intelligence neural networks Physics Hypercomplex

来源：评论

学校读者我要写书评

暂无评论

Improve accuracy in CNNs while using approximate computing methods

引用

JOURNAL OF SUPERCOMPUTING 2025年第2期81卷 1-23页

作者： Rafieinejad, Mohammadreza Marvasti, Mohammadreza Binesh Asghari, Seyyed Amir Shahbakhti, Kimiya Kharazmi Univ Dept Elect & Comp Engn Tehran Iran

artificial neural networks have been one of the science's most influential and essential branches in the past decades. neural networks have found applications in various fields including medical and pharmaceutical services, voice and speech recognition, computer vision, natural language processing, and video and image processing. neural networks have many layers and consume much energy. Approximate computing is a promising way to reduce energy consumption in applications that can tolerate a degree of accuracy reduction. This paper proposes an effective method to prevent accuracy reduction after using approximate computing methods in the CNNs. The method exploits the k-means clustering algorithm to label pixels in the first convolutional layer. Then, using one of the existing pruning methods, different pruning amounts have been applied to all layers. The experimental results on three CNNs and four different datasets show that the accuracy of the proposed method has significantly improved (by 17%) compared to the baseline network.

关键词： Approximate computing Computer vision Convolutional neural network Energy consumption Machine learning neural network

来源：评论

学校读者我要写书评

暂无评论

Foundation models in pathology

引用

PATHOLOGIE 2025年第3期46卷 152-155页

作者： Klauschen, Frederick Dippel, Jonas Mueller, Klaus-Robert Ludwig Maximilians Univ Munchen Pathol Inst Thalkirchner Str 36 D-80337 Munich Germany Berlin Inst Fdn Learning & Data BIFOLD Berlin Germany Bayer Zentrum Krebsforschung BZKF Munich Germany Tech Univ Berlin Machine Learning Grp Berlin Germany Aignostics GmbH Berlin Germany Korea Univ Dept Artificial Intelligence Seoul South Korea Max Planck Inst Informat Saarbrucken Germany

Foundation models prepare neural networks for applications in specific domains, such as speech applications or image analysis, through self-supervised pretraining. These models can be adapted for specific applications, such as histopathological diagnostics. While adaptation still requires supervised training, AI applications based on foundation models achieve significantly better prediction accuracy with fewer training data compared to conventional approaches. This article introduces the topic and provides an overview of foundation models in pathology.

关键词： artificial intelligence Computer-assisted image processing Histopathology Machine learning Machine learning Foundation models Foundation models neural networks neural networks Machine learning Foundation models neural networks

来源：评论

学校读者我要写书评

暂无评论

Balancing precision and efficiency: an approximate multiplier with built-in error compensation for error-resilient applications

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-17页

作者： Sayadi, Ladan Amirany, Abdolah Moaiyeri, Mohammad Hossein Timarchi, Somayeh Shahid Beheshti Univ Fac Elect Engn Tehran Iran George Washington Univ Dept Elect & Comp Engn Washington DC USA Queen Mary Univ London Sch Elect Engn & Comp Sci London E1 4NS England

In the pursuit of high-performance designs for error-resilient applications, approximate computing emerges as a key strategy. This paper introduces an innovative approximate multiplier, leveraging two highly efficient compressors. These compressors operate in tandem across two stages, strategically compensating for errors and culminating in a multiplier that maintains accuracy and significantly reduces delay in the final stage. The proposed method is specifically tailored for applications reliant on multiplication, such as image processing and neural networks. HSPICE simulations were conducted using 7 nm FinFET technology to gauge its efficacy. Results indicate a remarkable 82% reduction in power-delay product (PDP) compared to traditional multipliers. Moreover, system-level simulations underscore the practicality of the proposed multiplier in real-world applications like image processing and artificial intelligence, revealing minimal compromise in accuracy. This work contributes a nuanced perspective to approximate computing, presenting a multiplier poised to elevate efficiency without sacrificing precision in critical domains.

关键词： Approximate multiplier Approximate compressor Low-power design image processing neural networks

来源：评论

学校读者我要写书评

暂无评论

Fractal neural Network Approach for Analyzing Satellite images

引用

APPLIED artificial INTELLIGENCE 2025年第1期39卷

作者： Shymanskyi, Volodymyr Ratinskiy, Oleh Shakhovska, Nataliya Lviv Polytech Natl Univ Dept Artificial Intelligence Kn Romana Str 5 UA-79905 Lvov Ukraine

Satellites play a critical role in modern technology by providing images for various applications, such as detecting infrastructure and assessing environmental impacts. The author's work investigates the application of Fractal neural networks (FractalNet) for automating the detection of specific objects in satellite images. The study aims to improve processing speed and accuracy compared to traditional Convolutional neural networks (CNNs). The research involves developing and comparing FractalNet with CNNs, focusing on their effectiveness in image classification. The architecture of FractalNet, characterized by recursive structures and deep layers, is evaluated against CNNs like VGG16 and ResNet50. Data collection included manually gathering high-resolution satellite images of specific objects from Google Earth. The neural network models were trained and tested with varying hyperparameters, including learning rates and batch sizes. FractalNet demonstrated superior performance over CNNs, particularly in deep network configurations. The results improved significantly with data augmentation and optimized hyperparameters, achieving a test accuracy of up to 93.26% with a 32-layer model. Fractal neural networks offer a promising approach for automating satellite image analysis, providing better accuracy and robustness compared to traditional CNNs architectures.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Implementation of Kolmogorov-Arnold networks for Efficient image processing in Resource-Constrained Internet of Things Devices

引用

TECHNOLOGIES 2025年第4期13卷 155-155页

作者： Shaushenova, Anargul Kuznetsov, Oleksandr Nurpeisova, Ardak Ongarbayeva, Maral S Seifullin Kazakh Agro Tech Res Univ Fac Comp Syst & Profess Educ Dept Informat Syst Astana 010000 Kazakhstan eCampus Univ CO Dept Theoret & Appl Sci Via Isimbardi 10 I-22060 Novedrate CO Italy Kharkov Natl Univ Sch Comp Sci & Artificial Intelligence Dept Intelligent Software Syst & Technol 4 Svobody Sq UA-61022 Kharkiv Ukraine Int Taraz Univ Fac Nat Sci Dept Informat & Commun Technol Taraz 080000 Kazakhstan

This research investigates the implementation of Kolmogorov-Arnold networks (KANs) for image processing in resource-constrained IoTs devices. KANs represent a novel neural network architecture that offers significant advantages over traditional deep learning approaches, particularly in applications where computational resources are limited. Our study demonstrates the efficiency of KAN-based solutions for image analysis tasks in IoTs environments, providing comparative performance metrics against conventional convolutional neural networks. The experimental results indicate substantial improvements in processing speed and memory utilization while maintaining competitive accuracy. This work contributes to the advancement of AI-driven IoTs applications by proposing optimized KAN-based implementations suitable for edge computing scenarios. The findings have important implications for IoTs deployment in smart infrastructure, environmental monitoring, and industrial automation where efficient image processing is critical.

关键词： Kolmogorov-Arnold networks person detection visual wake words lightweight neural networks TinyML resource-constrained computing computer vision efficient inference hybrid neural architectures

来源：评论

学校读者我要写书评

暂无评论

Generative artificial Intelligence for Hyperspectral Sensor Data: A Review

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 6422-6439页

作者： Abuhani, Diaa Addeen Zualkernan, Imran Aldamani, Raghad Alshafai, Mohamed Amer Univ Sharjah Dept Comp Sci & Engn Sharjah 26666 U Arab Emirates

Airborne platforms and satellites provide rich sensor data in the form of hyperspectral images (HSI), which are crucial for numerous vision-related tasks, such as feature extraction, image enhancement, and data synthesis. This article reviews the contextual importance and applications of generative artificial intelligence (GAI) in the advancement of HSI processing. GAI methods address the inherent challenges of HSI data, such as high dimensionality, noise, and the need to preserve spectral-spatial correlations, rendering them indispensable for modern HSI analysis. Generative neural networks, including generative adversarial networks and denoising diffusion probabilistic models, are highlighted for their superior performance in classification, segmentation, and object identification tasks, often surpassing traditional approaches, such as U-Nets, autoencoders, and deep convolutional neural networks. Diffusion models showed competitive performance in tasks, such as feature extraction and image resolution enhancement, particularly in terms of inference time and computational cost. Transformer architectures combined with attention mechanisms further improved the accuracy of generative methods, particularly for preserving spectral and spatial information in tasks, such as image translation, data augmentation, and data synthesis. Despite these advancements, challenges remain, particularly in developing computationally efficient models for super-resolution and data synthesis. In addition, novel evaluation metrics tailored to the complex nature of HSI data are needed. This review underscores the potential of GAI in addressing these challenges while presenting its current strengths, limitations, and future research directions.

关键词： Feature extraction Hyperspectral imaging image segmentation Satellites Spatial resolution Machine learning neural networks Reviews Noise measurement Data models Diffusion models generative adversarial networks (GANs) generative artificial intelligence (GAI) generative neural networks (GNNs) hyperspectral images

来源：评论

学校读者我要写书评

暂无评论

An overview memristor based hardware accelerators for deep neural network

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2024年第9期36卷 e7997-e7997页

作者： Gokgoz, Baki Gul, Fatih Aydin, Tolga Gumushane Univ Torul Vocat Sch Dept Comp Technol Gumushane Turkiye Recep Tayyip Erdogan Univ Fac Engn & Architecture Elect & Elect Engn Rize Turkiye Ataturk Univ Fac Engn Comp Engn Erzurum Turkiye Recep Tayyip Erdogan Univ Dept Elect Elect Engn Rize Turkiye

The prevalence of artificial intelligence applications using artificial neural network architectures for functions such as natural language processing, text prediction, object detection, speech, and image recognition has significantly increased in today's world. The computational functions performed by artificial neural networks in classical applications require intensive and large-scale data movement between memory and processing units. Various software and hardware efforts are being made to perform these operations more efficiently. Despite these efforts, latency in data traffic and the substantial amount of energy consumed in data processing emerge as bottleneck disadvantages of the Von Neumann architecture. To overcome this bottleneck problem, it is necessary to develop hardware units specific to artificial intelligence applications. For this purpose, neuro-inspired computing chips are believed to provide an effective approach by designing and integrating a set of features inspired by neurobiological systems at the hardware level to address the problems arising in artificial intelligence applications. The most notable among these approaches is memristor-based neuromorphic computing systems. Memristors are seen as promising devices for hardware-level improvement in terms of speed and energy because they possess non-volatile memory and exhibit analog behavior. They enable effective storage and processing of synaptic weights, offering solutions for hardware-level development. Taking into account these advantages of memristors, this study examines the research conducted on artificial neural networks and hardware that can directly perform deep learning functions and mimic the biological brain, which is different from classical systems in today's context.

关键词： AI accelerators deep learning memristors neuromorphic computing synapses

来源：评论

学校读者我要写书评

暂无评论

Integration of Convolutional neural Network and image processing for Pulp Fibril Detection and Measurement

引用

IEEE ACCESS 2025年 13卷 74630-74642页

作者： Chirakitsakul, Tanachot Wattuya, Pakaket Somboon, Phichit Jansakra, Panthira Watcharopas, Chakrit Kasetsart Univ Dept Comp Sci Bangkok Thailand Kasetsart Univ Fac Sci Artificial Intelligence Technol & Innovat Ctr Hlth Bangkok 10900 Thailand Kasetsart Univ Dept Forest Prod Bangkok 10900 Thailand

The fibrillation index is a critical metric in paper manufacturing, quantifying the degree of fibrillation achieved during the pulp refining process. Optimizing this metric enhances both paper quality and production efficiency. However, traditional measurement methods-such as manual visual examination of pulp samples under microscopy-are slow, error-prone, and labor-intensive, limiting their scalability in industrial applications. This study proposes a novel method that integrates deep learning with image processing techniques to automate fibril detection and fibrillation index computation. The proposed method leverages the discriminative capabilities of convolutional neural networks (CNNs) with adaptive image processing techniques to overcome key challenges such as low contrast, image noise, and variability in fibril morphology. The patch-based classification approach effectively filters out irrelevant objects, especially those whose features visually resemble fibrils, thus improving fibril segmentation accuracy. The method was comprehensively validated against expert-labeled ground truth images and achieved a promising average error rate of 0.4494 +/- 0.4187. Experimental results also demonstrate the strong robustness of the proposed method, with consistent performance across diverse refining conditions and image qualities, making it suitable for real-world application in the pulp and paper industry. Furthermore, this study paves the way for broader applications in materials science and biomedical imaging, where precise feature detection in microscopic images is essential.

关键词： Optical fiber networks Optical fibers Optical fiber testing Indexes image processing Microscopy Refining Noise Feature extraction Length measurement Convolutional neural network deep learning image segmentation fibril detection pulp fibril analysis fibrillation index

来源：评论

学校读者我要写书评

暂无评论

Application of deep reinforcement learning in various image processing tasks: a survey

引用

EVOLVING SYSTEMS 2025年第1期16卷 1-20页

作者： Tadesse, Daniel Moges Kebede, Samuel Rahimeto Debele, Taye Girma Waldamichae, Fraol Gelana Ethiopian Artificial Intelligence Inst Addis Ababa 40782 Ethiopia Addis Ababa Sci & Technol Univ Coll Elect & Mech Engn Addis Ababa 120611 Ethiopia Debreberhan Univ Coll Engn Debreberhan 222 Ethiopia

A subset of machine learning algorithm called Deep Reinforcement Learning (DRL) enables computers or agents to learn behavior by taking actions in a given environment through trial and error while observing the rewards. In this learning paradigm, the agent is given a set of actions to chose and is then rewarded or punished depending on the results of those actions. The agent gradually develops the ability to make the best decisions by maximizing its rewards. DRL blends the learning ability of deep neural networks into the decision making capability of reinforcement learning (RL) frameworks in order to seeks and identify the most favorable set of actions. This survey paper studies DRL applications for diverse image processing tasks. It starts by providing an overview of the latest model-free and model-based RL and DRL algorithms. Then, it looks at how DRL is being used for various image processing tasks including image segmentation and classification, object detection, image registration, image denoising, image restoration, and landmark detection. Lastly, the paper discusses the potential uses and challenges of DRL in the proposed area by addressing the research questions. Survey results have showed that DRL is a promising approach for image processing and that it has the potential to solve complex image processing tasks.

关键词： Deep reinforcement learning Deep neural networks image processing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：